Predicting Cardiovascular Diseases Using Machine Learning Integrated with Feature Selection Through Blue Whale Optimization

Cardiovascular diseases (CVDs) continue to be a significant global health concern, demanding the creation of precise and timely prediction models for efficient disease treatment. In particular, the feature selection through the blue whale optimization algorithm is used in this study's early prediction in the classification of cardiovascular disorders utilizing machine learning techniques. Machine learning has become a potent tool for deciphering intricate medical data and producing precise forecasts. The blue whale optimization algorithm, a metaheuristic algorithm inspired by blue whale feeding behavior, is used in this study for feature selection. This algorithm enhances the effectiveness and performance of the prediction model by efficiently navigating the search space to locate the most pertinent information for CVD classification. The suggested process is broken down into various steps. An extensive dataset encompassing clinical data, demographic data, medical history, and the results of diagnostic tests is initially gathered from a wide range of patients. The most insightful characteristics from the dataset are then chosen using the blue whale optimization process, which lowers the model's dimensionality and improves its interpretability. The efficiency of the suggested methodology is shown by the experimental findings from real-world CVD datasets. In comparison to conventional methods, the machine learning model with feature selection through the blue whale optimization algorithm achieves higher accuracy and increased performance. This emphasizes the importance of using cutting-edge optimization strategies for feature selection in CVD classification.